检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wu, Zhengqian Li, Ruizhe Xu, Zijun Wang, Zhongyuan Xiao, Chunxia Liang, Chao School of Computer Science Wuhan University China School of Cyber Science and Engineering Wuhan University China National Engineering Research Center for Multimedia Software Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

ISBN: (纸本)157735897X

Video question answering (VideoQA) aims to answer natural language questions according to the given videos. Although existing models perform well in the factoid VideoQA task, they still face challenges in deep video understanding (DVU) task, which focuses on story videos. Compared to factoid videos, the most significant feature of story videos is storylines, which are composed of complex interactions and long-range evolvement of core story topics including characters, actions and locations. Understanding these topics requires models to possess DVU capability. However, existing DVU datasets rarely organize questions according to these story topics, making them difficult to comprehensively assess VideoQA models' DVU capability of complex storylines. Additionally, the question quantity and video length of these dataset are limited by high labor costs of handcrafted dataset building method. In this paper, we devise a large language model based multi-agent collaboration framework, StoryMind, to automatically generate a new large-scale DVU dataset. The dataset, FriendsQA, derived from the renowned sitcom Friends with an average episode length of 1,358 seconds, contains 44.6K questions evenly distributed across 14 fine-grained topics. Finally, We conduct comprehensive experiments on 10 state-of-the-art VideoQA models using the FriendsQA dataset. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Java Basic Thread Misuses Based on Static Event Analysis

Detection of Java Basic Thread Misuses Based on Static Event...

引用

IEEE International Conference on Automated software engineering (ASE)

作者： Baoquan Cui Miaomiao Wang Chi Zhang Jiwei Yan Jun Yan Jian Zhang State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Technology Center of Software Engineering Institute of Software Chinese Academy of Sciences Beijing China

The fundamental asynchronous thread (***. Thread) in Java can be easily misused, due to the lack of deep understanding for garbage collection and thread interruption mechanism. For example, a careless implementation of asynchronous thread may cause no response to the interrupt mechanism in time, resulting in unexpected thread-related behaviors, especially resource leak/waste. Currently, few works aim at these misuses and related works adopt either the dynamic approach which lacks effective inputs or the static path-sensitive approach with high time consumption due to the path explosion, causing false negatives. We have found that the behavior of threads and the interaction between threads and its referencing objects can be abstracted. In this paper, we propose an event analysis approach to detect the defects in Java programs and Android apps, which focuses on the existence or the order of the events to reduce the false negatives. We extract the misuse-related events, containing the thread events and the destroy events of the object referenced by the thread. Then we analyze the events with loop identification, happens-before relationship construction and alias determination. Finally, we implement an automatic tool named Leopard and evaluate it on real world Java programs and Android apps. Experiments show that it is efficient when comparing with the existing approach (misuse: 723 vs 47, time: 60s vs 30min), which also outperforms the existing work in precision. The manual check indicates that Leopard is more efficient and effective than existing work. Besides, 66 issues reported by us have been confirmed and 21 of them have been fixed by developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Spatio-Temporal Decision Fusion Network for Facial Expression Recognition 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Chen, Xuanchi Yang, Heng Zhang, Xia Zheng, Xiangwei Li, Wei School of Information Science and Engineering Shandong Normal University Jinan China Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China Internet Diagnosis and Treatment Center Taian City Central Hospital Taian China Shandong Normal University Library Shandong Normal University Jinan China

ISBN: (数字)9783031201028

ISBN: (纸本)9783031201011

Facial expression recognition (FER) becomes research focus in affective computing, as it already plays an important role in public security application scenarios such as urban safety management and safety driving assistance systems. Modeling the spatiotemporal information of facial expression sequences in a targeted manner, integrating and utilizing them appropriately is challenging. In this paper, a facial expression recognition method based on spatial-temporal decision fusion network (STDFN) is proposed. Firstly, the facial expression sequences are divided into four sub-sequences according to face regions, and BiLSTM are used for each of sub-sequences to extract local temporal features. The local morphological features of facial expressions can be captured in more detail to maximize the utilization of the temporal features of dynamic facial expressions. Then, VGG19 is utilized to extract the shallow spatial features of peak expression frame, and the channel weights of spatial features is assigned by squeeze-and-excitation module to attain the weighted spatial features. This allows valid spatial features to be purposefully retained to avoid overfitting. Finally, temporal features and spatial features are used separately calculating expression classification results. And a decision-level fusion module is designed to fuse the two results to obtain the final FER result. Extensive experimental results demonstrate that on three FER datasets CK+, Oulu-CASIA and MMI, achieves 98.83%, 89.31% and 82.86% accuracy, which proved that STDFN effectively improved the recognition accuracy of FER. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Graph Convolutional Network for Visual Reinforcement Learning of Action Detection 8

Heterogeneous Graph Convolutional Network for Visual Reinfor...

引用

8th International Conference on Automation, Control and Robotics engineering, CACRE 2023

作者： Wang, Liangliang Huang, Chengxi Chen, Xinwei Wuhan University of Technology School of Computer Science and Artificial Intelligence Luoshi Road 122 Wuhan430070 China -HIT Research Institute of Engineering and Technology Building 9 Software Park Quanzhou362008 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798350302776

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive Robot 8

Recognizing Human-object Interactions for a Home Assistive R...

引用

8th International Conference on Automation, Control and Robotics engineering, CACRE 2023

作者： Wang, Liangliang Huo, Guanglei Chen, Xinwei Huang, Chengxi Wuhan University of Technology School of Computer Science and Artificial Intelligence Luoshi Road 122 Wuhan430070 China -HIT Research Institute of Engineering and Technology Building 9 Software Park Quanzhou362008 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798350302776

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot - Xiaozhi II verify its robustness. © 2023 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Ant: An Efficient Lossless Compression Algorithm for IoT Time Series Data

Ant: An Efficient Lossless Compression Algorithm for IoT Tim...

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Junhui Li Guangping Xu Hongzhang Yang Yulei Wu School of Computer Science and Engineering Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education China Faculty of Science and Engineering University of Bristol Bristol U.K

In various applications in Internet of Things like industrial monitoring, large amounts of floating-point time series data are generated at an unprecedented rate. Efficient compression algorithms can effectively reduce the size of data, enhance transmission performance and storage efficiency, and simultaneously lower storage costs. Therefore, there is a need for lightweight and efficient stream compression algorithms. In this paper, we propose a novel lossless floating-point data compression algorithm called Ant. The main idea is to encode double-precision floating-point numbers into integer form, calculate the delta between adjacent values, and then convert the delta into unsigned integers. This encoding method effectively reduces storage costs and improves data compression efficiency. Extensive experiments on real-world datasets demonstrate that our algorithm achieves compression speeds at least as fast as state-of-the-art streaming methods, and a 63% relative improvement in average compression rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Imperceptible Face Forgery Attack via Adversarial Semantic Mask

arXiv

引用

arXiv 2024年

作者： Liu, Decheng Su, Qixuan Peng, Chunlei Wang, Nannan Gao, Xinbo State Key Laboratory of Integrated Services Networks School of Cyber Engineering Xidian University Shaanxi Xi’an710071 China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai201112 China State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Xidian University Shaanxi Xi’an710071 China Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing400065 China

With the great development of generative model techniques, face forgery detection draws more and more attention in the related field. Researchers find that existing face forgery models are still vulnerable to adversarial examples with generated pixel perturbations in the global image. These generated adversarial samples still can't achieve satisfactory performance because of the high detectability. To address these problems, we propose an Adversarial Semantic Mask Attack framework (ASMA) which can generate adversarial examples with good transferability and invisibility. Specifically, we propose a novel adversarial semantic mask generative model, which can constrain generated perturbations in local semantic regions for good stealthiness. The designed adaptive semantic mask selection strategy can effectively leverage the class activation values of different semantic regions, and further ensure better attack transferability and stealthiness. Extensive experiments on the public face forgery dataset prove the proposed method achieves superior performance compared with several representative adversarial attack methods. The code is publicly available at https://***/clawerO-O/ASMA. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A General Debiasing Framework with Counterfactual Reasoning for Multimodal Public Speaking Anxiety Detection

SSRN

引用

SSRN 2024年

作者： Zhang, Tingting Zhu, Yangfu Wu, Bin Zheng, Chunping Tan, Jiachen Xiong, Zihua Beijing Key Laboratory of Intelligent Telecommunication Software and Multimedia School of Computer Science National Pilot School of Software Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Humanities Beijing University of Posts and Telecommunications Beijing100876 China

Multimodal public speaking anxiety detection (MPSAD), which aims to identify the anxiety states of learners, has attracted widespread attention. Unfortunately, the current MPSAD task inevitably suffers from the impact of latent different types of multimodal hybrid biases, such as context bias, label bias and keyword bias. Models may rely on these biases as shortcuts, preventing them from fully utilizing all three modalities to learn multimodal knowledge. Existing methods primarily focus on addressing specific types of biases, but anticipating bias types when designing these methods is challenging, as we cannot foresee all possible biases. To tackle this issue, we use causal graphs to clarify the causal relationships among variables, and propose a General Multimodal Counterfactual Reasoning debiasing framework (GMCR), which eliminates multimodal hybrid biases from a unified causal perspective. Specifically, this plug-and-play debiasing framework removes multimodal hybrid biases by disentangling causal and biased features and capturing adverse effects via a counterfactual branch. It then subtracts spurious correlations during inference for unbiased predictions. Due to the challenge of collecting speech video data, there are currently limited high-quality datasets available for the MPSAD task. To overcome this scarcity, we create a new large-scale fine-grained Multimodal English Public Speaking Anxiety (ME-PSA) dataset. Extensive experiments on our ME-PSA and two benchmarks demonstrate the superior effectiveness of our proposed framework. Furthermore, our approach improves the accuracy and F1 score of the MPSAD task by over 2.00% and 4.00%, respectively, compared to the vanilla SOTA baselines. Our dataset and code will be available at https://***/Ztt1997/GMCR\_Framework. © 2024, The Authors. All rights reserved.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading

arXiv

引用

arXiv 2024年

作者： Zhang, Wenhao Wang, Jun Luo, Yong Yu, Lei Yu, Wei He, Zheng Shen, Jialie School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Electronics and Information Wuhan University China Department of Computer Science City University of London United Kingdom

Lip-reading is to utilize the visual information of the speaker’s lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledg...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Haoxiang Ma Modi Shi Boyang Gao Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China Geometry Robotics

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen ob-jects using the grasp distribution learned from the training set, they often exhibit a significant performance drop when encountering objects with diverse shapes and struc-tures. To enhance the grasp detection methods' general-ization ability, we incorporate domain prior knowledge of robotic grasping, enabling better adaptation to objects with significant shape and structure differences. More specifi-cally, we employ the physical constraint regularization during the training phase to guide the model towards predicting grasps that comply with the physical rule on grasping. For the unstable grasp poses predicted on novel objects, we design a contact-score joint optimization using the pro-jection contact map to refine these poses in cluttered sce-narios. Extensive experiments conducted on the GraspNet-1 billion benchmark demonstrate a substantial performance gain on the novel object set and the real-world grasping experiments also demonstrate the effectiveness of our gen-eralizing 6-DoF grasp detection method. Code is available at https://***/mahaoxiang822/Generalizing-Grasp.

关键词： Training computer vision Shape Grasping Benchmark testing Predictive models Performance gain

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：